Bias Discovery in Machine Learning Models for Mental Health

TL;DR

This paper investigates bias in machine learning models for mental health, demonstrating gender bias in predictions and applying fairness mitigation strategies to clinical data, marking a novel contribution in psychiatric AI applications.

Contribution

It introduces the first analysis of bias and mitigation strategies in machine learning models trained on real clinical psychiatry data.

Findings

Gender bias was identified in benzodiazepine prediction models.

Bias mitigation strategies like reweighing improved fairness metrics.

Model performance was affected by bias mitigation techniques.

Abstract

Fairness and bias are crucial concepts in artificial intelligence, yet they are relatively ignored in machine learning applications in clinical psychiatry. We computed fairness metrics and present bias mitigation strategies using a model trained on clinical mental health data. We collected structured data related to the admission, diagnosis, and treatment of patients in the psychiatry department of the University Medical Center Utrecht. We trained a machine learning model to predict future administrations of benzodiazepines on the basis of past data. We found that gender plays an unexpected role in the predictions-this constitutes bias. Using the AI Fairness 360 package, we implemented reweighing and discrimination-aware regularization as bias mitigation strategies, and we explored their implications for model performance. This is the first application of bias exploration and mitigation in a machine learning model trained on real clinical psychiatry data.